© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. MLP
    9. 6-MLP
    11. 3885
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    import module name

    python-code · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 256 tokens each
    Dataset (Dashboard)
    neuronpedia/python-code-simplified
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ()
    -0.07
    label
    -0.06
     label
    -0.06
    :
    -0.05
    ")
    -0.05
    ~
    -0.04
    ')
    -0.04
    :↵
    -0.04
    -
    -0.03
    #
    -0.03
    POSITIVE LOGITS
    ).
    0.04
    it
    0.04
    its
    0.03
    qu
    0.02
    new
    0.02
     #
    0.02
    mb
    0.01
    ver
    0.01
    ger
    0.01
    import
    0.01
    Activations Density 10.587%

    No Known Activations